How to Use the Moneybird MCP in Pydantic AI

Q: How do I register the Moneybird MCP Server with Pydantic AI?

Use the MCPToolset class with your HTTP server URL and pass it to your Pydantic AI Agent's toolsets argument. This registers all Moneybird accounting tools while enforcing strict runtime type-checking on their outputs.

Achieve zero-error Moneybird accounting with Pydantic AI by validating every invoice and ledger mutation at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moneybird MCP to Pydantic AI

Create your Vinkius account to connect Moneybird to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Moneybird with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Financial Auditing via Pydantic AI

The `list_ledger_accounts` tool pulls your complete chart of Moneybird accounts directly into Pydantic AI's strict validation engine. This MCP server setup enforces strict Python type validation on every single response from `list_ledger_accounts` and `list_financial_mutations` before Pydantic AI processes it. Your Pydantic AI agent checks the Moneybird data structure before your code executes the transaction. If Moneybird returns an unexpected ledger field, Pydantic AI raises a validation error instantly instead of corrupting your books.

Strict Contact and Estimate Management

The `create_contact` tool registers new clients in Moneybird while enforcing strict Pydantic AI schema requirements at runtime. The Pydantic AI agent uses `create_contact` to build profiles, verifying that phone numbers, emails, and tax IDs match your strict Python schemas before pushing to Moneybird. When checking Moneybird proposals, the Pydantic AI agent runs `list_estimates` and `list_contacts` to map deals to accounts. If a Moneybird contact record is missing required fields, Pydantic AI blocks the action before an invalid estimate is sent.

Bulletproof Sales and Purchase Invoice Pipelines

The `list_invoices` tool retrieves your complete Moneybird sales history to build type-safe revenue dashboards in Pydantic AI. The Pydantic AI agent tracks incoming revenue and expenses by querying `list_invoices` and `list_purchase_invoices` to build real-time Moneybird financial statements. It checks recurring templates using `list_recurring_invoices` and looks up specific line items with `get_invoice` to populate Pydantic AI models. Every Moneybird transaction is parsed into a strongly typed Python model, preventing bad billing data from entering your Pydantic AI pipeline.

Setup guide

Set up Moneybird MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "moneybird-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Moneybird tools.",
)

result = await agent.run("List recent Moneybird transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Moneybird. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Moneybird now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Moneybird MCP in Pydantic AI

Use the `MCPToolset` class with your HTTP server URL and pass it to your Pydantic AI Agent's `toolsets` argument. This registers all Moneybird accounting tools while enforcing strict runtime type-checking on their outputs.

The Pydantic AI agent will raise a validation error immediately. Because Pydantic AI enforces strict schemas on tools like Moneybird `list_financial_mutations`, you are completely protected against silent data corruption in your ledger.

Yes, the toolset integrates directly into the Pydantic AI async runtime. This lets your agent fetch Moneybird `list_invoices` and `list_purchase_invoices` concurrently without blocking your main application loop.

The server handles pagination under the hood when your Pydantic AI agent calls Moneybird `list_estimates`. It returns structured lists that fit your Python schema, letting your agent process them in manageable chunks.

Your raw Moneybird financial mutations and ledger accounts are processed entirely in memory within an ephemeral, single-tenant V8 sandbox. No Pydantic AI payload history is cached, stored, or exposed to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript